# Deep Photonic Reservoir Computer for Speech Recognition

arXiv: https://arxiv.org/abs/2312.06558 · HTML: https://mlsanity.com/paper/2312.06558/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2023.

## Built on by (most cited first, 5 of 5)

- [Efficient Optimisation of Physical Reservoir Computers using only a Delayed Input](https://mlsanity.com/paper/2401.14371/) (2024)
- [Beyond Terabit/s Integrated Neuromorphic Photonic Processor for DSP-Free Optical Interconnects](https://mlsanity.com/paper/2504.15044/) (2025)
- [Hardware-Software Collaborative Computing of Photonic Spiking Reinforcement Learning for Robotic Continuous Control](https://mlsanity.com/paper/2512.00427/) (2025)
- [Vestibular reservoir computing](https://mlsanity.com/paper/2604.09943/) (2026)
- [Direct Raw Audio Signal Processing via Reservoir Computing: An Investigation into 'Feature-Free' Architectures](https://mlsanity.com/paper/2606.21335/) (2026)

## Abstract (arXiv)

Speech recognition is a critical task in the field of artificial intelligence and has witnessed remarkable advancements thanks to large and complex neural networks, whose training process typically requires massive amounts of labeled data and computationally intensive operations. An alternative paradigm, reservoir computing, is energy efficient and is well adapted to implementation in physical substrates, but exhibits limitations in performance when compared to more resource-intensive machine learning algorithms. In this work we address this challenge by investigating different architectures of interconnected reservoirs, all falling under the umbrella of deep reservoir computing. We propose a photonic-based deep reservoir computer and evaluate its effectiveness on different speech recognition tasks. We show specific design choices that aim to simplify the practical implementation of a reservoir computer while simultaneously achieving high-speed processing of high-dimensional audio signals. Overall, with the present work we hope to help the advancement of low-power and high-performance neuromorphic hardware.